Researchers at the University of Colorado at Boulder, in the United States, have developed an intelligent cane that can help blind people with complicated tasks, such as finding the ideal seat in a cafeteria or choosing a product on a supermarket shelf.
- Scientists create robotic arm capable of finding even items lost in a purse
- Lysa: learn about the Brazilian project for a robot guide with GPS for the blind
According to the engineers, the equipment will be an important tool in helping visually impaired people who need to move around in a world entirely designed for sighted humans, facilitating not only displacement but also interaction with these environments.
“I really enjoy shopping and spend a lot of time in the store, but I realize that not many people can do it, making this simple process really restrictive. However, we believe that this is a problem that can be solved”, explains doctoral student in computer science Shivendra Agrawal, lead author of the study.
The smart device developed by the scientists is very similar to a conventional cane for the blind. The main difference is in the camera and attached sensors that use computer vision technology to map and catalog the environment around it.
This set manages to guide the user through vibrations in the handle and spoken instructions in real time. Phrases like “turn right” or “go up a little to your left” help the user to find their way around a restaurant or in front of a shelf full of different products.
“Artificial intelligence and computer vision are improving and people are using them to build self-driving cars and similar inventions. However, these technologies also have the potential to improve the quality of life for many people,” adds Agrawal.
During the simulations carried out in the laboratory, the researchers improvised two different situations: in the first one, they created an environment similar to a cafe with tables and chairs around it. In the second, they set up a shelf filled with boxes of different cereals.
Tests showed that when moving around inside the restaurant, volunteers using the smart canes were able to find the right chair in 10 out of 12 attempts. Already when they were in front of the shelf, all participants were able to scan and reach the desired product.
“We still need a laptop in a backpack to run the AI software, but the idea is to make the system more compact to work with a regular smartphone. Our objective is to mature this technology, as we believe that assisted robotics has the potential to change the reality of many people”, concludes Agrawal.
Source: University of Colorado